3.1 tensorflow学习与应用——非线性回归

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
x_data = np.linspace(-0.5, 0.5, 200)[:, np.newaxis]
noise = np.random.normal(0, 0.02, x_data.shape)
y_data = np.square(x_data) + noise

x = tf.placeholder(tf.float32, [None, 1])
y = tf.placeholder(tf.float32, [None, 1])

w1 = tf.Variable(tf.random_normal([1, 10]))
b1 = tf.Variable(tf.zeros([1, 10]))
input1 = tf.matmul(x, w1) + b1
L1 = tf.nn.tanh(input1)

w2 = tf.Variable(tf.random_normal([10, 1]))
b2 = tf.Variable(tf.zeros([1, 1]))
input2 = tf.matmul(L1, w2) + b2
prediction = tf.nn.tanh(input2)

loss = tf.reduce_mean(tf.square(y - prediction))
optimizer = tf.train.GradientDescentOptimizer(0.2)
result = optimizer.minimize(loss)
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for _ in range(2000):
        sess.run(result, feed_dict={x: x_data, y: y_data})
    prediction_value = sess.run(prediction, feed_dict={x :x_data})
    plt.figure()
    plt.scatter(x_data, y_data)
    plt.plot(x_data, prediction_value, 'r-', lw = 5)
    plt.show()